Suvaansh_bhambri Multi Level Compositional Reasoning for Interactive Instruction Following 2023

[TOC]

1. Title: Multi-Level Compositional Reasoning for Interactive Instruction Following
2. Author: Suvaansh Bhambri et. al.
3. Publish Year: 2023
4. Review Date: Fri, Mar 3, 2023
5. url: https://ppolon.github.io/paper/aaai2023-alfred-mocha.pdf

Summary of paper

Motivation

• The task given to the agents are often composite thus are challenging as completing them require to reason about multiple subtasks.

Contribution

• we propose to divide and conquer it by breaking the task into multiple subgoals and attend to them individually for better navigation and interaction.
• at the highest level, we infer a sequence of human-interpreatable subgoals to be executed based on the language instructions by a high-level policy composition controller.
• at the middle level, we discriminatively control the agent’s navigation by a master policy by alternating between a navigation policy and various independent interaction policies.
• finally, at the lowest level, we infer manipulation actions with the corresponding object masks using appropriate interaction policy.

Model